© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19351
    Prev
    Next
    INDEX
    Explanations

    operators in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.08
    ary
    -0.07
    erÃŃa
    -0.07
    -quarters
    -0.06
    ilden
    -0.05
    ़
    -0.05
    ernt
    -0.05
    ambu
    -0.05
    èĬª
    -0.05
    teenth
    -0.05
    POSITIVE LOGITS
    ivity
    0.07
    rch
    0.07
    pite
    0.07
    ships
    0.06
    ariat
    0.06
     vigilant
    0.06
    onom
    0.06
    óż
    0.06
    inaldo
    0.06
    vind
    0.06
    Activations Density 0.006%

    No Known Activations